© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7525
    Prev
    Next
    INDEX
    Explanations

    references to minimal or minimized concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nodeValue
    -0.38
    ixen
    -0.37
    postmedia
    -0.37
     stroll
    -0.36
    enis
    -0.36
    ConverterFactory
    -0.35
    anone
    -0.35
    bular
    -0.35
    dung
    -0.34
    corbic
    -0.34
    POSITIVE LOGITS
     minimal
    1.63
    minimal
    1.41
    Minimal
    1.37
     Minimal
    1.35
     minimum
    1.17
     minimale
    1.12
     минима
    1.10
    minimum
    1.04
     mínimo
    1.02
     mínima
    0.99
    Activations Density 0.233%

    No Known Activations